© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14000
    Prev
    Next
    INDEX
    Explanations

    say "byte"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prices
    -15.88
    个工作
    -15.88
    销量
    -15.69
    .Connect
    -15.63
    的工作
    -15.50
     priced
    -15.50
    portfolio
    -15.44
    quo
    -15.38
     nerv
    -15.19
    rossover
    -15.06
    POSITIVE LOGITS
     bytes
    25.25
     Bytes
    24.88
    BitFields
    24.38
     Header
    24.25
     byte
    24.00
    hdr
    23.88
    _byte
    23.63
    -byte
    23.63
    bytes
    23.50
    .byte
    23.13
    Activations Density 0.498%

    No Known Activations